End-to-End UAV Navigation Method Based on Bio-Inspired D-LGMD Looming Cue

doi:10.3778/j.issn.1002-8331.2312-0309

Abstract

Abstract: To address a series of challenges in UAV(unmanned aerial vehicle) navigation problem, including the limited adaptability to varying conditions, the delay of responses, the huge workload of system debugging, and the difficultiy of integrating multiple-modules, this study proposes an end-to-end method for autonomous drone flight. This method employs bio-inspired distributed presynaptic connection-lobula giant movement detector(D-LGMD) looming cues as the primary sensory input, using A* algorithm paths as learning labels. Through the minimum jerk trajectory optimization and geometric trajectory control, the proposed approach achieves intelligent navigation for drones in intricate settings. Experimental results demonstrate that incorporating looming cues with motion information significantly reduces the path loss. The results confirm that this method performs distinct advantages over traditional techniques and leading end-to-end approaches.

Key words: unmanned aerial vehicle(UAV), autonomous flight, end-to-end, distributed presynaptic connection-lobula giant movement detector(D-LGMD), intelligent navigation, bio-inspired

摘要： 针对复杂场景下传统无人机自主飞行存在模块化资源难以整合、环境适应性有限而导致系统调试工作量大、响应迟缓的问题，该研究提出一种端到端的无人机自主飞行方法。该方法将生物启发式D（distributed presynaptic connection）-LGMD（lobula giant movement detector）迫近线索作为主要感知输入，以A*算法路径作为学习标签，经过最小急动轨迹优化和几何轨迹控制处理，实现复杂环境下的无人机智能导航。实验结果表明，融入带有运动信息的迫近线索可显著降低路径损失，并证明了该方法相比传统方法和领先的端到端方法具有明显的优势。

关键词: 无人机, 自主飞行, 端到端, D-LGMD, 智能导航, 生物启发式

ZHAO Jiannan, PANG Delin, ZHAO Qidong, LI Zhiteng, CHEN Shaonan, YUE Shigang, SHUANG Feng. End-to-End UAV Navigation Method Based on Bio-Inspired D-LGMD Looming Cue[J]. Computer Engineering and Applications, 2025, 61(7): 370-378.

赵剑楠, 庞德霖, 赵启东, 李志腾, 陈绍南, 岳士岗, 双丰. 生物启发式D-LGMD迫近线索的无人机端到端智能导航[J]. 计算机工程与应用, 2025, 61(7): 370-378.

References

[1] LI Z T, ZHAO J N, ZHOU X, et al. RTSDM: a real-time semantic dense mapping system for UAVs[J]. Machines, 2022, 10(4): 285.
[2] MEYER-DELIUS D, BEINHOFER M, BURGARD W, et al. Occupancy grid models for robot mapping in changing environments[C]//Proceedings of the 26th AAAI Conference on Artificial Intelligence. New York: ACM, 2012: 2024-2030.
[3] HORNUNG A, WURM K M, BENNEWITZ M, et al. OctoMap: an efficient probabilistic 3D mapping framework based on octrees[J]. Autonomous Robots, 2013, 34(3): 189-206.
[4] HART P E, NILSSON N J, RAPHAEL B. A formal basis for the heuristic determination of minimum cost paths[J]. IEEE Transactions on Systems Science and Cybernetics, 1968, 4(2): 100-107.
[5] DOLGOV D, THRUN S, MONTEMERLO M, et al. Practical search techniques in path planning for autonomous driving[J]. Ann Arbor, 2008, 1001(48105): 18-80.
[6] KUFFNER J, RRT S L V. RRT-connect: an efficient approach to single-query path planning[C]//Proceedings of the IEEE International Conference on Robotics and Automation, 2000: 473-479.
[7] 李昱奇, 刘志乾, 程凝怡, 等. 多约束条件下无人机航迹规划[J]. 计算机工程与应用, 2021, 57(4): 225-230.
LI Y Q, LIU Z Q, CHENG N Y, et al. Path planning of UAV under multi-constraint conditions[J]. Computer Engineering and Applications, 2021, 57(4): 225-230.
[8] KYRIAKOPOULOS K J, SARIDIS G N. Minimum jerk path generation[C]//Proceedings of the 1988 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 1988: 364-369.
[9] MELLINGER D, KUMAR V. Minimum snap trajectory generation and control for quadrotors[C]//Proceedings of the 2011 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2011: 2520-2525.
[10] QIN S J, BADGWELL T A. An overview of industrial model predictive control technology[C]//Proceedings of the International Conference on Chemical Process Control, 1997.
[11] ZHOU B Y, GAO F, WANG L Q, et al. Robust and efficient quadrotor trajectory generation for fast autonomous flight[J]. IEEE Robotics and Automation Letters, 2019, 4(4): 3529-3536.
[12] ZHOU X, WANG Z P, YE H K, et al. EGO-planner: an ESDF-free gradient-based local planner for quadrotors[J]. IEEE Robotics and Automation Letters, 2020, 6(2): 478-485.
[13] BOJARSKI M, DEL TESTA D, DWORAKOWSKI D, et al. End to end learning for self-driving cars[J]. arXiv:1604. 07316, 2016.
[14] CODEVILLA F, MüLLER M, LóPEZ A, et al. End-to-end driving via conditional imitation learning[C]//Proceedings of the 2018 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2018: 4693-4700.
[15] LOQUERCIO A, MAQUEDA A I, DEL-BLANCO C R, et al. DroNet: learning to fly by driving[J]. IEEE Robotics and Automation Letters, 2018, 3(2): 1088-1095.
[16] LOQUERCIO A, KAUFMANN E, RANFTL R, et al. Learning high-speed flight in the wild[J]. Science Robotics, 2021, 6(59): eabg5810.
[17] 郭迟, 罗宾汉, 李飞, 等. 类脑导航算法: 综述与验证[J]. 武汉大学学报(信息科学版), 2021, 46(12): 1819-1831.
GUO C, LUO B H, LI F, et al. Review and verification for brain-like navigation algorithm[J]. Geomatics and Information Science of Wuhan University, 2021, 46(12): 1819-1831.
[18] RIND F C, BRAMWELL D I. Neural network based on the input organization of an identified neuron signaling impending collision[J]. Journal of Neurophysiology, 1996, 75(3): 967-985.
[19] ZHAO J N, WANG H X, BELLOTTO N, et al. Enhancing LGMD’s looming selectivity for UAV with spatial-temporal distributed presynaptic connections[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(5): 2539-2553.
[20] 马兴灶, 赵剑楠, 朱齐媛, 等. 基于LGMD的无人机避障方法研究[J]. 计算机工程与应用, 2019, 55(15): 250-256.
MA X Z, ZHAO J N, ZHU Q Y, et al. Study on obstacle avoidance method of UAV based on LGMD[J]. Computer Engineering and Applications, 2019, 55(15): 250-256.
[21] USENKO V, VON STUMBERG L, PANGERCIC A, et al. Real-time trajectory replanning for MAVs using uniform B-splines and a 3D circular buffer[C]//Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway: IEEE, 2017: 215-222.
[22] LEE T, LEOK M, MCCLAMROCH N H. Geometric tracking control of a quadrotor UAV on SE(3)[C]//Proceedings of the 49th IEEE Conference on Decision and Control. Piscataway: IEEE, 2010: 5420-5425.
[23] 杨凌耀, 张爱华, 张洁, 等. 栅格地图环境下机器人速度势实时路径规划[J]. 计算机工程与应用, 2021, 57(24): 290-295.
YANG L Y, ZHANG A H, ZHANG J, et al. Real-time path planning of velocity potential for robot in grid map environment[J]. Computer Engineering and Applications, 2021, 57(24): 290-295.